Research map / Reinforcement learning / Visual and representation RL
CleanRL: High-quality Single-file Implementations of Deep Reinforcement Learning Algorithms
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Single-file implementation of PPO (ppo_atari.py, 337 LOC) instead of modular library design | PPO on Atari (Breakout) · Atari Breakout | performance matching SB3 PPO | No clear effect |
| Adding invalid action masking implemented within the single-file code | PPO prototype for games with parameterized action spaces · development effort | lines of code required | Helped |
Closest papers by meaning
- CORL: Research-oriented Deep Offline Reinforcement Learning Library (NeurIPS 2023 · similarity 0.85)
- Towards General-Purpose Model-Free Reinforcement Learning (ICLR 2025 · similarity 0.84)
- Co-Adaptation of Algorithmic and Implementational Innovations in Inference-based Deep Reinforcement Learning (NeurIPS 2021 · similarity 0.84)
- RICE: Breaking Through the Training Bottlenecks of Reinforcement Learning with Explanation (ICML 2024 · similarity 0.84)
- Symmetric Replay Training: Enhancing Sample Efficiency in Deep Reinforcement Learning for Combinatorial Optimization (ICML 2024 · similarity 0.83)
- Cleanba: A Reproducible and Efficient Distributed Reinforcement Learning Platform (ICLR 2024 · similarity 0.83)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.